© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 229451
    Prev
    Next
    INDEX
    Explanations

    many languages

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xis
    0.41
    ỹ
    0.39
    鲲
    0.38
     oda
    0.37
     Woodrow
    0.37
    INTRO
    0.37
    ẽ
    0.35
    深度
    0.35
    óloga
    0.35
     SISO
    0.35
    POSITIVE LOGITS
     ly
    0.49
     kie
    0.48
     শুনানি
    0.41
    ನ್ನು
    0.38
    واكب
    0.38
     UNI
    0.38
     exceptions
    0.37
     Century
    0.37
     poi
    0.37
    ولي
    0.37
    Activations Density 0.000%

    No Known Activations